Benchmarking reports

from sklearn_benchmarks.report import Reporting
import pandas as pd
pd.set_option('display.max_colwidth', None)
pd.set_option('display.max_columns', None)
pd.set_option('display.max_rows', None)

reporting = Reporting(config_file_path="config.yml")
reporting.run()

Time report

	hour	min	sec
algo
KNeighborsClassifier	0.0	14.0	3.525326
daal4py_KNeighborsClassifier	0.0	3.0	7.207122
KNeighborsClassifier_kd_tree	0.0	6.0	12.574277
daal4py_KNeighborsClassifier_kd_tree	0.0	1.0	39.063415
KMeans_tall	0.0	1.0	37.948737
daal4py_KMeans_tall	0.0	1.0	11.784298
KMeans_short	0.0	0.0	17.437895
daal4py_KMeans_short	0.0	0.0	7.610057
LogisticRegression	0.0	0.0	58.422084
daal4py_LogisticRegression	0.0	0.0	52.107584
Ridge	0.0	0.0	0.966038
daal4py_Ridge	0.0	0.0	0.649127
total	0.0	30.0	9.369231

KNeighborsClassifier vs daal4py

Results

	estimator	function	mean_sklearn	stdev_sklearn	n_samples_train	n_samples	n_features	algorithm	n_jobs	n_neighbors	accuracy_score_sklearn	accuracy_score_daal4py	mean_daal4py	stdev_daal4py	speedup	stdev_speedup	profiling
0	KNeighborsClassifier	fit	0.137	0.002	1000000	1000000	100	brute	-1	1	NaN	NaN	0.480	0.003	0.285	0.000	See
1	KNeighborsClassifier	predict	0.162	0.013	1000000	1	100	brute	-1	1	1.0	1.0	0.086	0.002	1.889	0.007	See
2	KNeighborsClassifier	predict	25.170	0.701	1000000	1000	100	brute	-1	1	1.0	1.0	1.843	0.074	13.659	0.002	See
3	KNeighborsClassifier	fit	0.130	0.004	1000000	1000000	100	brute	-1	5	NaN	NaN	0.479	0.009	0.271	0.001	See
4	KNeighborsClassifier	predict	0.168	0.016	1000000	1	100	brute	-1	5	1.0	1.0	0.083	0.001	2.035	0.009	See
5	KNeighborsClassifier	predict	33.982	0.000	1000000	1000	100	brute	-1	5	1.0	1.0	1.807	0.053	18.809	0.001	See
6	KNeighborsClassifier	fit	0.129	0.004	1000000	1000000	100	brute	-1	100	NaN	NaN	0.475	0.007	0.272	0.001	See
7	KNeighborsClassifier	predict	0.168	0.015	1000000	1	100	brute	-1	100	1.0	1.0	0.083	0.002	2.041	0.009	See
8	KNeighborsClassifier	predict	34.145	0.000	1000000	1000	100	brute	-1	100	1.0	1.0	1.850	0.047	18.457	0.001	See
9	KNeighborsClassifier	fit	0.127	0.003	1000000	1000000	100	brute	1	1	NaN	NaN	0.484	0.010	0.262	0.001	See
10	KNeighborsClassifier	predict	0.175	0.002	1000000	1	100	brute	1	1	1.0	1.0	0.080	0.000	2.176	0.000	See
11	KNeighborsClassifier	predict	12.510	0.122	1000000	1000	100	brute	1	1	1.0	1.0	1.854	0.044	6.748	0.001	See
12	KNeighborsClassifier	fit	0.134	0.004	1000000	1000000	100	brute	1	5	NaN	NaN	0.467	0.003	0.287	0.001	See
13	KNeighborsClassifier	predict	0.185	0.002	1000000	1	100	brute	1	5	1.0	1.0	0.082	0.003	2.269	0.001	See
14	KNeighborsClassifier	predict	23.377	0.387	1000000	1000	100	brute	1	5	1.0	1.0	1.798	0.038	13.003	0.001	See
15	KNeighborsClassifier	fit	0.129	0.004	1000000	1000000	100	brute	1	100	NaN	NaN	0.481	0.008	0.269	0.001	See
16	KNeighborsClassifier	predict	0.186	0.002	1000000	1	100	brute	1	100	1.0	1.0	0.081	0.001	2.300	0.000	See
17	KNeighborsClassifier	predict	23.162	0.110	1000000	1000	100	brute	1	100	1.0	1.0	1.845	0.052	12.552	0.001	See
18	KNeighborsClassifier	fit	0.050	0.001	1000000	1000000	2	brute	-1	1	NaN	NaN	0.094	0.006	0.535	0.005	See
19	KNeighborsClassifier	predict	0.018	0.003	1000000	1	2	brute	-1	1	1.0	1.0	0.005	0.001	3.359	0.089	See
20	KNeighborsClassifier	predict	20.803	0.016	1000000	1000	2	brute	-1	1	1.0	1.0	0.274	0.017	76.054	0.004	See
21	KNeighborsClassifier	fit	0.049	0.002	1000000	1000000	2	brute	-1	5	NaN	NaN	0.104	0.003	0.474	0.002	See
22	KNeighborsClassifier	predict	0.032	0.003	1000000	1	2	brute	-1	5	1.0	1.0	0.006	0.001	5.339	0.051	See
23	KNeighborsClassifier	predict	28.892	0.076	1000000	1000	2	brute	-1	5	1.0	1.0	0.266	0.005	108.698	0.000	See
24	KNeighborsClassifier	fit	0.054	0.001	1000000	1000000	2	brute	-1	100	NaN	NaN	0.094	0.003	0.575	0.002	See
25	KNeighborsClassifier	predict	0.033	0.002	1000000	1	2	brute	-1	100	1.0	1.0	0.005	0.001	6.174	0.021	See
26	KNeighborsClassifier	predict	29.099	0.015	1000000	1000	2	brute	-1	100	1.0	1.0	0.316	0.006	92.119	0.000	See
27	KNeighborsClassifier	fit	0.053	0.001	1000000	1000000	2	brute	1	1	NaN	NaN	0.096	0.003	0.556	0.001	See
28	KNeighborsClassifier	predict	0.013	0.001	1000000	1	2	brute	1	1	1.0	1.0	0.006	0.001	2.257	0.017	See
29	KNeighborsClassifier	predict	10.025	0.093	1000000	1000	2	brute	1	1	1.0	1.0	0.284	0.009	35.360	0.001	See
30	KNeighborsClassifier	fit	0.054	0.002	1000000	1000000	2	brute	1	5	NaN	NaN	0.100	0.003	0.542	0.002	See
31	KNeighborsClassifier	predict	0.028	0.001	1000000	1	2	brute	1	5	1.0	1.0	0.006	0.001	4.537	0.014	See
32	KNeighborsClassifier	predict	18.928	0.212	1000000	1000	2	brute	1	5	1.0	1.0	0.289	0.007	65.517	0.001	See
33	KNeighborsClassifier	fit	0.065	0.003	1000000	1000000	2	brute	1	100	NaN	NaN	0.094	0.003	0.694	0.003	See
34	KNeighborsClassifier	predict	0.028	0.002	1000000	1	2	brute	1	100	1.0	1.0	0.006	0.001	4.587	0.012	See
35	KNeighborsClassifier	predict	18.632	0.397	1000000	1000	2	brute	1	100	1.0	1.0	0.345	0.011	54.040	0.001	See

Plots

Shared hyperparameters:

	value
algorithm	brute

KNeighborsClassifier_kd_tree vs daal4py

Results

	estimator	function	mean_sklearn	stdev_sklearn	n_samples_train	n_samples	n_features	algorithm	n_jobs	n_neighbors	accuracy_score_sklearn	accuracy_score_daal4py	mean_daal4py	stdev_daal4py	speedup	stdev_speedup	profiling
0	KNeighborsClassifier_kd_tree	fit	2.794	0.091	1000000	1000000	10	kd_tree	-1	1	NaN	NaN	0.691	0.023	4.045	0.002	See
1	KNeighborsClassifier_kd_tree	predict	0.002	0.000	1000000	1	10	kd_tree	-1	1	1.0	1.0	0.000	0.000	8.917	0.169	See
2	KNeighborsClassifier_kd_tree	predict	0.434	0.009	1000000	1000	10	kd_tree	-1	1	1.0	1.0	0.094	0.002	4.596	0.001	See
3	KNeighborsClassifier_kd_tree	fit	2.730	0.069	1000000	1000000	10	kd_tree	-1	5	NaN	NaN	0.689	0.011	3.962	0.001	See
4	KNeighborsClassifier_kd_tree	predict	0.003	0.001	1000000	1	10	kd_tree	-1	5	1.0	1.0	0.000	0.000	9.699	0.329	See
5	KNeighborsClassifier_kd_tree	predict	0.842	0.015	1000000	1000	10	kd_tree	-1	5	1.0	1.0	0.179	0.002	4.707	0.000	See
6	KNeighborsClassifier_kd_tree	fit	3.021	0.067	1000000	1000000	10	kd_tree	-1	100	NaN	NaN	0.685	0.029	4.409	0.002	See
7	KNeighborsClassifier_kd_tree	predict	0.004	0.001	1000000	1	10	kd_tree	-1	100	1.0	1.0	0.001	0.000	3.977	0.153	See
8	KNeighborsClassifier_kd_tree	predict	2.699	0.051	1000000	1000	10	kd_tree	-1	100	1.0	1.0	0.537	0.015	5.026	0.001	See
9	KNeighborsClassifier_kd_tree	fit	2.710	0.116	1000000	1000000	10	kd_tree	1	1	NaN	NaN	0.699	0.022	3.874	0.003	See
10	KNeighborsClassifier_kd_tree	predict	0.001	0.000	1000000	1	10	kd_tree	1	1	1.0	1.0	0.000	0.000	3.491	0.325	See
11	KNeighborsClassifier_kd_tree	predict	0.700	0.019	1000000	1000	10	kd_tree	1	1	1.0	1.0	0.096	0.003	7.259	0.002	See
12	KNeighborsClassifier_kd_tree	fit	2.749	0.130	1000000	1000000	10	kd_tree	1	5	NaN	NaN	0.700	0.014	3.930	0.003	See
13	KNeighborsClassifier_kd_tree	predict	0.001	0.000	1000000	1	10	kd_tree	1	5	1.0	1.0	0.000	0.000	3.300	0.301	See
14	KNeighborsClassifier_kd_tree	predict	1.292	0.051	1000000	1000	10	kd_tree	1	5	1.0	1.0	0.181	0.004	7.125	0.002	See
15	KNeighborsClassifier_kd_tree	fit	2.733	0.097	1000000	1000000	10	kd_tree	1	100	NaN	NaN	0.747	0.025	3.657	0.002	See
16	KNeighborsClassifier_kd_tree	predict	0.002	0.001	1000000	1	10	kd_tree	1	100	1.0	1.0	0.001	0.000	2.061	0.246	See
17	KNeighborsClassifier_kd_tree	predict	4.392	0.152	1000000	1000	10	kd_tree	1	100	1.0	1.0	0.562	0.012	7.812	0.002	See
18	KNeighborsClassifier_kd_tree	fit	1.228	0.037	1000000	1000000	2	kd_tree	-1	1	NaN	NaN	0.490	0.010	2.506	0.001	See
19	KNeighborsClassifier_kd_tree	predict	0.002	0.001	1000000	1	2	kd_tree	-1	1	1.0	1.0	0.000	0.000	18.935	0.477	See
20	KNeighborsClassifier_kd_tree	predict	0.027	0.001	1000000	1000	2	kd_tree	-1	1	1.0	1.0	0.001	0.000	24.024	0.141	See
21	KNeighborsClassifier_kd_tree	fit	1.201	0.037	1000000	1000000	2	kd_tree	-1	5	NaN	NaN	0.507	0.012	2.369	0.002	See
22	KNeighborsClassifier_kd_tree	predict	0.002	0.000	1000000	1	2	kd_tree	-1	5	1.0	1.0	0.000	0.000	18.402	0.498	See
23	KNeighborsClassifier_kd_tree	predict	0.028	0.001	1000000	1000	2	kd_tree	-1	5	1.0	1.0	0.001	0.000	21.763	0.149	See
24	KNeighborsClassifier_kd_tree	fit	1.198	0.058	1000000	1000000	2	kd_tree	-1	100	NaN	NaN	0.504	0.019	2.376	0.004	See
25	KNeighborsClassifier_kd_tree	predict	0.003	0.001	1000000	1	2	kd_tree	-1	100	1.0	1.0	0.000	0.000	19.251	0.531	See
26	KNeighborsClassifier_kd_tree	predict	0.043	0.001	1000000	1000	2	kd_tree	-1	100	1.0	1.0	0.009	0.002	5.031	0.046	See
27	KNeighborsClassifier_kd_tree	fit	1.140	0.037	1000000	1000000	2	kd_tree	1	1	NaN	NaN	0.481	0.013	2.367	0.002	See
28	KNeighborsClassifier_kd_tree	predict	0.001	0.000	1000000	1	2	kd_tree	1	1	1.0	1.0	0.000	0.000	5.157	0.457	See
29	KNeighborsClassifier_kd_tree	predict	0.025	0.001	1000000	1000	2	kd_tree	1	1	1.0	1.0	0.001	0.000	26.555	0.085	See
30	KNeighborsClassifier_kd_tree	fit	1.179	0.041	1000000	1000000	2	kd_tree	1	5	NaN	NaN	0.474	0.014	2.485	0.002	See
31	KNeighborsClassifier_kd_tree	predict	0.001	0.000	1000000	1	2	kd_tree	1	5	1.0	1.0	0.000	0.000	5.612	0.524	See
32	KNeighborsClassifier_kd_tree	predict	0.025	0.001	1000000	1000	2	kd_tree	1	5	1.0	1.0	0.001	0.000	19.607	0.137	See
33	KNeighborsClassifier_kd_tree	fit	1.169	0.028	1000000	1000000	2	kd_tree	1	100	NaN	NaN	0.479	0.013	2.441	0.001	See
34	KNeighborsClassifier_kd_tree	predict	0.001	0.000	1000000	1	2	kd_tree	1	100	1.0	1.0	0.000	0.000	5.217	0.496	See
35	KNeighborsClassifier_kd_tree	predict	0.051	0.002	1000000	1000	2	kd_tree	1	100	1.0	1.0	0.007	0.001	7.135	0.036	See

Plots

Shared hyperparameters:

	value
algorithm	kd_tree

KMeans_tall vs daal4py

Results

	estimator	function	mean_sklearn	stdev_sklearn	n_samples_train	n_samples	n_features	algorithm	init	max_iter	n_clusters	n_init	tol	n_iter_sklearn	adjusted_rand_score_sklearn	n_iter_daal4py	adjusted_rand_score_daal4py	mean_daal4py	stdev_daal4py	speedup	stdev_speedup	profiling
0	KMeans_tall	fit	0.605	0.015	1000000	1000000	2	full	k-means++	30	3	1	0.0	30.0	NaN	30.0	NaN	0.431	0.026	1.403	0.004	See
1	KMeans_tall	predict	0.000	0.000	1000000	1	2	full	k-means++	30	3	1	0.0	NaN	1.0	NaN	1.0	0.000	0.000	2.015	0.511	See
2	KMeans_tall	predict	0.000	0.000	1000000	1000	2	full	k-means++	30	3	1	0.0	NaN	1.0	NaN	1.0	0.000	0.000	1.956	0.403	See
3	KMeans_tall	fit	0.523	0.018	1000000	1000000	2	full	random	30	3	1	0.0	30.0	NaN	30.0	NaN	0.397	0.016	1.315	0.003	See
4	KMeans_tall	predict	0.000	0.000	1000000	1	2	full	random	30	3	1	0.0	NaN	1.0	NaN	1.0	0.000	0.000	2.398	0.503	See
5	KMeans_tall	predict	0.000	0.000	1000000	1000	2	full	random	30	3	1	0.0	NaN	1.0	NaN	1.0	0.000	0.000	2.191	0.504	See
6	KMeans_tall	fit	6.119	0.098	1000000	1000000	100	full	k-means++	30	3	1	0.0	30.0	NaN	30.0	NaN	2.873	0.042	2.130	0.000	See
7	KMeans_tall	predict	0.000	0.000	1000000	1	100	full	k-means++	30	3	1	0.0	NaN	1.0	NaN	1.0	0.000	0.000	2.142	0.510	See
8	KMeans_tall	predict	0.001	0.000	1000000	1000	100	full	k-means++	30	3	1	0.0	NaN	1.0	NaN	1.0	0.000	0.000	2.183	0.527	See
9	KMeans_tall	fit	5.684	0.109	1000000	1000000	100	full	random	30	3	1	0.0	30.0	NaN	30.0	NaN	2.688	0.043	2.114	0.001	See
10	KMeans_tall	predict	0.000	0.000	1000000	1	100	full	random	30	3	1	0.0	NaN	1.0	NaN	1.0	0.000	0.000	2.316	0.421	See
11	KMeans_tall	predict	0.001	0.000	1000000	1000	100	full	random	30	3	1	0.0	NaN	1.0	NaN	1.0	0.000	0.000	2.345	0.242	See

Plots

Shared hyperparameters:

	value
algorithm	full
n_clusters	3
max_iter	30
n_init	1
tol	0.0

KMeans_short vs daal4py

Results

	estimator	function	mean_sklearn	stdev_sklearn	n_samples_train	n_samples	n_features	algorithm	init	max_iter	n_clusters	n_init	tol	n_iter_sklearn	adjusted_rand_score_sklearn	n_iter_daal4py	adjusted_rand_score_daal4py	mean_daal4py	stdev_daal4py	speedup	stdev_speedup	profiling
0	KMeans_short	fit	0.298	0.019	10000	10000	2	full	k-means++	30	300	1	0.0	30.0	NaN	22.0	NaN	0.095	0.005	3.134	0.007	See
1	KMeans_short	predict	0.000	0.000	10000	1	2	full	k-means++	30	300	1	0.0	NaN	1.0	NaN	1.0	0.000	0.000	1.919	0.439	See
2	KMeans_short	predict	0.001	0.000	10000	1000	2	full	k-means++	30	300	1	0.0	NaN	1.0	NaN	1.0	0.001	0.000	1.219	0.138	See
3	KMeans_short	fit	0.110	0.004	10000	10000	2	full	random	30	300	1	0.0	30.0	NaN	30.0	NaN	0.041	0.002	2.665	0.003	See
4	KMeans_short	predict	0.000	0.000	10000	1	2	full	random	30	300	1	0.0	NaN	1.0	NaN	1.0	0.000	0.000	2.040	0.512	See
5	KMeans_short	predict	0.001	0.000	10000	1000	2	full	random	30	300	1	0.0	NaN	1.0	NaN	1.0	0.001	0.000	1.145	0.183	See
6	KMeans_short	fit	0.759	0.028	10000	10000	100	full	k-means++	30	300	1	0.0	19.0	NaN	19.0	NaN	0.326	0.021	2.328	0.006	See
7	KMeans_short	predict	0.000	0.000	10000	1	100	full	k-means++	30	300	1	0.0	NaN	1.0	NaN	1.0	0.000	0.000	1.971	0.427	See
8	KMeans_short	predict	0.005	0.001	10000	1000	100	full	k-means++	30	300	1	0.0	NaN	1.0	NaN	1.0	0.001	0.000	3.667	0.165	See
9	KMeans_short	fit	0.230	0.022	10000	10000	100	full	random	30	300	1	0.0	27.0	NaN	30.0	NaN	0.170	0.014	1.357	0.016	See
10	KMeans_short	predict	0.000	0.000	10000	1	100	full	random	30	300	1	0.0	NaN	1.0	NaN	1.0	0.000	0.000	1.946	0.351	See
11	KMeans_short	predict	0.003	0.001	10000	1000	100	full	random	30	300	1	0.0	NaN	1.0	NaN	1.0	0.001	0.000	2.405	0.285	See

Plots

Shared hyperparameters:

	value
algorithm	full
n_clusters	300
max_iter	30
n_init	1
tol	0.0

LogisticRegression vs daal4py

Results

	estimator	function	mean_sklearn	stdev_sklearn	n_samples_train	n_samples	n_features	C	class_weight	dual	fit_intercept	intercept_scaling	l1_ratio	max_iter	multi_class	n_jobs	penalty	random_state	solver	tol	verbose	warm_start	n_iter	mean_daal4py	stdev_daal4py	speedup	stdev_speedup	profiling
0	LogisticRegression	fit	10.624	0.043	1000000	1000000	100	1.0	NaN	False	True	1	NaN	100	auto	NaN	l2	NaN	lbfgs	0.0	0	False	[20]	10.929	0.253	0.972	0.001	See
1	LogisticRegression	predict	0.000	0.000	1000000	1	100	1.0	NaN	False	True	1	NaN	100	auto	NaN	l2	NaN	lbfgs	0.0	0	False	NaN	0.000	0.000	0.373	0.733	See
2	LogisticRegression	predict	0.000	0.000	1000000	1000	100	1.0	NaN	False	True	1	NaN	100	auto	NaN	l2	NaN	lbfgs	0.0	0	False	NaN	0.000	0.000	0.959	0.256	See
3	LogisticRegression	fit	0.693	0.022	1000	1000	10000	1.0	NaN	False	True	1	NaN	100	auto	NaN	l2	NaN	lbfgs	0.0	0	False	[26]	0.742	0.040	0.935	0.004	See
4	LogisticRegression	predict	0.000	0.000	1000	1	10000	1.0	NaN	False	True	1	NaN	100	auto	NaN	l2	NaN	lbfgs	0.0	0	False	NaN	0.001	0.001	0.093	1.461	See
5	LogisticRegression	predict	0.002	0.000	1000	100	10000	1.0	NaN	False	True	1	NaN	100	auto	NaN	l2	NaN	lbfgs	0.0	0	False	NaN	0.004	0.000	0.430	0.041	See

Plots

Shared hyperparameters:

	value
penalty	l2
dual	False
tol	0.0001
C	1.0
fit_intercept	True
intercept_scaling	1
class_weight	NaN
random_state	NaN
solver	lbfgs
max_iter	100
multi_class	auto
verbose	0
warm_start	False
n_jobs	NaN
l1_ratio	NaN

Ridge vs daal4py

Results

	estimator	function	mean_sklearn	stdev_sklearn	n_samples_train	n_samples	n_features	alpha	copy_X	fit_intercept	max_iter	normalize	random_state	solver	tol	n_iter	mean_daal4py	stdev_daal4py	speedup	stdev_speedup	profiling
0	Ridge	fit	0.038	0.001	1000	1000	1000	1.0	True	True	NaN	False	NaN	auto	0.001	NaN	0.021	0.001	1.820	0.003	See
1	Ridge	predict	0.000	0.000	1000	1	1000	1.0	True	True	NaN	False	NaN	auto	0.001	NaN	0.000	0.000	0.637	1.191	See
2	Ridge	predict	0.000	0.000	1000	100	1000	1.0	True	True	NaN	False	NaN	auto	0.001	NaN	0.000	0.000	0.677	0.376	See
3	Ridge	fit	0.008	0.000	10000	10000	100	1.0	True	True	NaN	False	NaN	auto	0.001	NaN	0.005	0.003	1.532	0.283	See
4	Ridge	predict	0.000	0.000	10000	1	100	1.0	True	True	NaN	False	NaN	auto	0.001	NaN	0.000	0.000	0.652	1.239	See
5	Ridge	predict	0.000	0.000	10000	1000	100	1.0	True	True	NaN	False	NaN	auto	0.001	NaN	0.000	0.000	0.681	0.356	See

Plots

Shared hyperparameters:

	value
alpha	1.0
fit_intercept	True
normalize	False
copy_X	True
max_iter	NaN
tol	0.001
solver	auto
random_state	NaN

Environment information

{
  "system_info": {
    "python": "3.8.8 | packaged by conda-forge | (default, Feb 20 2021, 16:22:27)  [GCC 9.3.0]",
    "executable": "/usr/share/miniconda/envs/sklbench/bin/python",
    "machine": "Linux-5.4.0-1046-azure-x86_64-with-glibc2.10"
  },
  "dependencies_info": {
    "pip": "21.1",
    "setuptools": "49.6.0.post20210108",
    "sklearn": "0.24.1",
    "numpy": "1.20.2",
    "scipy": "1.6.2",
    "Cython": null,
    "pandas": "1.2.4",
    "matplotlib": null,
    "joblib": "1.0.1",
    "threadpoolctl": "2.1.0"
  },
  "threadpool_info": [
    {
      "filepath": "/usr/share/miniconda/envs/sklbench/lib/libopenblasp-r0.3.12.so",
      "prefix": "libopenblas",
      "user_api": "blas",
      "internal_api": "openblas",
      "version": "0.3.12",
      "num_threads": 2,
      "threading_layer": "pthreads"
    },
    {
      "filepath": "/usr/share/miniconda/envs/sklbench/lib/libgomp.so.1.0.0",
      "prefix": "libgomp",
      "user_api": "openmp",
      "internal_api": "openmp",
      "version": null,
      "num_threads": 2
    }
  ],
  "cpu_count": 2
}